RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication
Capítulo o parte de un libro (BookPart)
Page Segmentation of Structured Documents Using 2D Stochastic Context-Free Grammars
n this paper we define a bidimensional extension of Stochastic Context-Free Grammars for page segmentation of structured documents. Two sets of text classification features are used to perform an initial classification of each zone of the page. Then, the page segmentation is obtained as the most likely hypothesis according to a grammar. This approach is compared to Conditional Random Fields and results show significant improvements in several cases. Furthermore, grammars provide a detailed segmentation that allowed a semantic evaluation which also validates this model., Work partially supported by the Spanish MEC under the
STraDA research project (TIN2012-37475-C02-01), the MITTRAL (TIN2009-
14633-C03-01) project, the Spanish projects TIN2009-14633-C03-01/03 and 2010-
CONES-00029, the FPU grant (AP2009-4363), by the Generalitat Valenciana
under the grant Prometeo/2009/014, and through the EU 7th Framework Programme grant tranScriptorium (Ref: 600707)